san-digital / tokspur
Private chat and code on your Mac. Run a 177B model on a 128 GB M5 Max: local Qwen3.8 Flash-Next inference with a 65,536-token context, Tokspur's own Metal engine with native MTP, and an OpenAI-compatible API. Apache 2.0.
Why this job: topics: apple-silicon, local-llm, llm-inference, gguf, inference-engine, on-device-ai
What it does
Tokspur runs Qwen3.8 Flash-Next locally on a Mac. It uses a native Metal worker and serves an OpenAI-compatible chat API.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 2 days ago
- Stars
- 13
- On GitHub
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- Mac
- From the latest release
- Latest version
- v0.1.0
- Released 2 days ago
- Built with
- C++
- 54% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- None
- No issues filed
- Pull requests
- 3 merged
- 0 waiting
- Releases
- 1
- 1 in the last year
- No contributing guide
- Security policy (opens in new tab)
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| incoai / splash | 2,185 | 5 days ago | Apache-2.0 | Mac |
| carloslfu / slotstream | 663 | 2 days ago | MIT | No downloads |
| StayLameBro / backburner | 1,180 | 4 days ago | MIT | No downloads |
More: download files, languages, topics, project record and preview image
Languages
- C++ 54%
- Rust 23%
- Metal 10%
- Objective-C++ 6%
Topics
- apple-silicon
- gguf
- llm
- local-inference
- macos
- metal
- openai-compatible
- qwen
- rust
- inference-engine
- llm-inference
- local-llm
Project record
- JobLocal LLMs
- StatusNew to our list
- Commits5
- Forks2
- Watching2
- CreatedNov 9, 2026
- First seen by usNov 10, 2026
- CheckedNov 11, 2026